Skip to content
conftrace_

Sébastien Arnold

3 papers · 2019–2021 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

NeurIPS (2) AISTATS (1)

Top co-authors

Guneet Dhillon (1) Stefano Soatto (1) Ioannis Mitliagkas (1) Avinash Ravichandran (1) Shariq Iqbal (1) Pierre-antoine Manzagol (1) Reza Babanezhad Harikandeh (1) Nicolas Le Roux (1) Fei Sha (1)

Research topics

Artificial Intelligence (2) Deep Learning (2) Machine Learning (2) Learning Paradigms (2) Mathematics & Optimization (1) Architectures (1) Core Methods (1) Optimization (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1)

Keywords

few-shot learning (2) stochastic optimization (1) curriculum learning (1) neural network optimization (1) gradient descent (1) online optimization (1) variance reduction (1) episodic training (1) heavy ball (1) implicit gradient transport (1) episode sampling (1) model-agnostic meta-learning (1) gradient transport (1)

Papers

Uniform Sampling over Episode Difficulty NeurIPS 2021 When MAML Can Adapt Fast and How to Assist When It Cannot AISTATS 2021 Reducing the variance in online optimization by transporting past gradients NeurIPS 2019